You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hello Gregor, i got this error while i'm trying to predict the result using fis.model.predict(X)
Input to reshape is a tensor with 32 values, but the requested shape has 1
[[{{node myanfis/sumLayer/Reshape}}]] [Op:__inference_predict_function_154498]
May i know why? And what should i do regarding this matter? Thank you!
The text was updated successfully, but these errors were encountered:
Hello @LorisAlif!
Thanks for pointing that out. In a recent push (ffb1120) I improved this.
The tensorflow model needs to know the batch_size of the input. So whenever you use fis.model.predict(X) you need to enter the correct batch_size as argument. Alternatively, you could simply type fis(X) and it does the job automatically.
Unfortunately with this implementation in keras, we are limited to use the same batch_size in training as in the prediction. I am not very happy with this but couldn't find a better alternative.
Hello Gregor, i got this error while i'm trying to predict the result using fis.model.predict(X)
Input to reshape is a tensor with 32 values, but the requested shape has 1
[[{{node myanfis/sumLayer/Reshape}}]] [Op:__inference_predict_function_154498]
May i know why? And what should i do regarding this matter? Thank you!
The text was updated successfully, but these errors were encountered: